[Readme] Update ChatQnA Readme for LLM Endpoint (#1086)

Signed-off-by: letonghan <letong.han@intel.com>
opea-project · Nov 11, 2024 · aa314f6 · aa314f6
1 parent 3744bb8
commit aa314f6
Show file tree

Hide file tree

Showing 4 changed files with 14 additions and 20 deletions.
diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/README.md b/ChatQnA/docker_compose/intel/cpu/xeon/README.md
@@ -26,7 +26,6 @@ To set up environment variables for deploying ChatQnA services, follow these ste
    export http_proxy="Your_HTTP_Proxy"
    export https_proxy="Your_HTTPs_Proxy"
    # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
-   # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
    export no_proxy="Your_No_Proxy",chatqna-xeon-ui-server,chatqna-xeon-backend-server,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm_service
    ```
 
@@ -324,17 +323,17 @@ For details on how to verify the correctness of the response, refer to [how-to-v
 
    ```bash
    # TGI service
-   curl http://${host_ip}:9009/generate \
+   curl http://${host_ip}:9009/v1/chat/completions \
      -X POST \
-     -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \
+     -d '{"model": "Intel/neural-chat-7b-v3-3", "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens":17}' \
      -H 'Content-Type: application/json'
    ```
 
    ```bash
    # vLLM Service
-   curl http://${host_ip}:9009/v1/completions \
+   curl http://${host_ip}:9009/v1/chat/completions \
      -H "Content-Type: application/json" \
-     -d '{"model": "Intel/neural-chat-7b-v3-3", "prompt": "What is Deep Learning?", "max_tokens": 32, "temperature": 0}'
+     -d '{"model": "Intel/neural-chat-7b-v3-3", "messages": [{"role": "user", "content": "What is Deep Learning?"}]}'
    ```
 
 5. MegaService

diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/README_qdrant.md b/ChatQnA/docker_compose/intel/cpu/xeon/README_qdrant.md
@@ -252,9 +252,9 @@ For details on how to verify the correctness of the response, refer to [how-to-v
    Then try the `cURL` command below to validate TGI.
 
    ```bash
-   curl http://${host_ip}:6042/generate \
+   curl http://${host_ip}:6042/v1/chat/completions \
      -X POST \
-     -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \
+     -d '{"model": "Intel/neural-chat-7b-v3-3", "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens":17}' \
      -H 'Content-Type: application/json'
    ```
 

diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/README.md b/ChatQnA/docker_compose/intel/hpu/gaudi/README.md
@@ -326,23 +326,18 @@ For validation details, please refer to [how-to-validate_service](./how_to_valid
    Then try the `cURL` command below to validate services.
 
    ```bash
-   #TGI Service
-   curl http://${host_ip}:8005/generate \
+   # TGI service
+   curl http://${host_ip}:9009/v1/chat/completions \
      -X POST \
-     -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":64, "do_sample": true}}' \
+     -d '{"model": ${LLM_MODEL_ID}, "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens":17}' \
      -H 'Content-Type: application/json'
    ```
 
    ```bash
-   #vLLM Service
-   curl http://${host_ip}:8007/v1/completions \
+   # vLLM Service
+   curl http://${host_ip}:9009/v1/chat/completions \
      -H "Content-Type: application/json" \
-     -d '{
-     "model": "${LLM_MODEL_ID}",
-     "prompt": "What is Deep Learning?",
-     "max_tokens": 32,
-     "temperature": 0
-     }'
+     -d '{"model": ${LLM_MODEL_ID}, "messages": [{"role": "user", "content": "What is Deep Learning?"}]}'
    ```
 
 5. MegaService

diff --git a/ChatQnA/docker_compose/nvidia/gpu/README.md b/ChatQnA/docker_compose/nvidia/gpu/README.md
@@ -238,9 +238,9 @@ docker compose up -d
    Then try the `cURL` command below to validate TGI.
 
    ```bash
-   curl http://${host_ip}:8008/generate \
+   curl http://${host_ip}:9009/v1/chat/completions \
      -X POST \
-     -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":64, "do_sample": true}}' \
+     -d '{"model": "Intel/neural-chat-7b-v3-3", "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens":17}' \
      -H 'Content-Type: application/json'
    ```